Student Performance Prediction using Machine Learning Model

An end-to-end Artificial Intelligence and Machine Learning project designed to predict student academic outcomes and provide data-driven insights. Key Highlights of the Development Process: • Outlier Analysis: Performed robust statistical detection to identify values deviating significantly from the average distribution. • Data Cleaning: Successfully quantified and isolated 552 outlier rows, which accounted for 8.36% of the total dataset. • Model Optimization: Dropped outlier indices and reset the dataframe index to enhance model robustness, eliminate biased data, and prevent skewed prediction results. Technologies Used: • Python (Pandas, NumPy, Scikit-Learn) • Machine Learning & Predictive Modeling • Data Preprocessing & Statistical Analysis